Mohammad Gheshlaghi Azar

Publication Activity (10 Years)

Years Active: 2010-2024
Publications (10 Years): 44

Top Topics

Credit Assignment

Policy Gradient

Reinforcement Learning

Top Venues

Publications

Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub, Eugene Choi, Chris Cremer, Arash Ahmadian, Yash Chandak, Mohammad Gheshlaghi Azar, Olivier Pietquin, Matthieu Geist
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion. CoRR (2024)
Mohammad Gheshlaghi Azar, Zhaohan Daniel Guo, Bilal Piot, Rémi Munos, Mark Rowland, Michal Valko, Daniele Calandriello
A General Theoretical Paradigm to Understand Learning from Human Preferences. AISTATS (2024)
Nathan Grinsztajn, Yannis Flet-Berliac, Mohammad Gheshlaghi Azar, Florian Strub, Bill Wu, Eugene Choi, Chris Cremer, Arash Ahmadian, Yash Chandak, Olivier Pietquin, Matthieu Geist
Averaging log-likelihoods in direct alignment. CoRR (2024)
Eugene Choi, Arash Ahmadian, Matthieu Geist, Olivier Pietquin, Mohammad Gheshlaghi Azar
Self-Improving Robust Preference Optimization. CoRR (2024)
Pierre Harvey Richemond, Yunhao Tang, Daniel Guo, Daniele Calandriello, Mohammad Gheshlaghi Azar, Rafael Rafailov, Bernardo Ávila Pires, Eugene Tarassov, Lucas Spangher, Will Ellsworth, Aliaksei Severyn, Jonathan Mallinson, Lior Shani, Gil Shamir, Rishabh Joshi, Tianqi Liu, Rémi Munos, Bilal Piot
Offline Regularised Reinforcement Learning for Large Language Models Alignment. CoRR (2024)
Rémi Munos, Michal Valko, Daniele Calandriello, Mohammad Gheshlaghi Azar, Mark Rowland, Zhaohan Daniel Guo, Yunhao Tang, Matthieu Geist, Thomas Mesnard, Andrea Michi, Marco Selvi, Sertan Girgin, Nikola Momchev, Olivier Bachem, Daniel J. Mankowitz, Doina Precup, Bilal Piot
Nash Learning from Human Feedback. CoRR (2023)
Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond, Bernardo Ávila Pires, Yash Chandak, Rémi Munos, Mark Rowland, Mohammad Gheshlaghi Azar, Charline Le Lan, Clare Lyle, András György, Shantanu Thakoor, Will Dabney, Bilal Piot, Daniele Calandriello, Michal Valko
Understanding Self-Predictive Learning for Reinforcement Learning. ICML (2023)
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard, Michal Valko, Wenhao Yang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári, Wataru Kumagai, Yutaka Matsuo
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice. CoRR (2023)
Mark Rowland, Rémi Munos, Mohammad Gheshlaghi Azar, Yunhao Tang, Georg Ostrovski, Anna Harutyunyan, Karl Tuyls, Marc G. Bellemare, Will Dabney
An Analysis of Quantile Temporal-Difference Learning. CoRR (2023)
Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, Daniel Guo, Daniele Calandriello, Michal Valko, Rémi Munos
A General Theoretical Paradigm to Understand Learning from Human Preferences. CoRR (2023)
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard, Michal Valko, Wenhao Yang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári, Wataru Kumagai, Yutaka Matsuo
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice. ICML (2023)
Zhaohan Guo, Shantanu Thakoor, Miruna Pislar, Bernardo Ávila Pires, Florent Altché, Corentin Tallec, Alaa Saade, Daniele Calandriello, Jean-Bastien Grill, Yunhao Tang, Michal Valko, Rémi Munos, Mohammad Gheshlaghi Azar, Bilal Piot
BYOL-Explore: Exploration by Bootstrapped Prediction. NeurIPS (2022)
Zhaohan Daniel Guo, Shantanu Thakoor, Miruna Pislar, Bernardo Ávila Pires, Florent Altché, Corentin Tallec, Alaa Saade, Daniele Calandriello, Jean-Bastien Grill, Yunhao Tang, Michal Valko, Rémi Munos, Mohammad Gheshlaghi Azar, Bilal Piot
BYOL-Explore: Exploration by Bootstrapped Prediction. CoRR (2022)
Tadashi Kozuno, Wenhao Yang, Nino Vieillard, Toshinori Kitamura, Yunhao Tang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Michal Valko, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári
KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal. CoRR (2022)
Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond, Bernardo Ávila Pires, Yash Chandak, Rémi Munos, Mark Rowland, Mohammad Gheshlaghi Azar, Charline Le Lan, Clare Lyle, András György, Shantanu Thakoor, Will Dabney, Bilal Piot, Daniele Calandriello, Michal Valko
Understanding Self-Predictive Learning for Reinforcement Learning. CoRR (2022)
Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Mehdi Azabou, Eva L. Dyer, Rémi Munos, Petar Velickovic, Michal Valko
Large-Scale Representation Learning on Graphs via Bootstrapping. ICLR (2022)
Ran Liu, Mehdi Azabou, Max Dabagia, Chi-Heng Lin, Mohammad Gheshlaghi Azar, Keith B. Hengen, Michal Valko, Eva L. Dyer
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity. CoRR (2021)
Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Rémi Munos, Petar Velickovic, Michal Valko
Bootstrapped Representation Learning on Graphs. CoRR (2021)
Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Alaa Saade, Shantanu Thakoor, Bilal Piot, Bernardo Ávila Pires, Michal Valko, Thomas Mesnard, Tor Lattimore, Rémi Munos
Geometric Entropic Exploration. CoRR (2021)
Mehdi Azabou, Mohammad Gheshlaghi Azar, Ran Liu, Chi-Heng Lin, Erik C. Johnson, Kiran Bhaskaran-Nair, Max Dabagia, Keith B. Hengen, William R. Gray Roncal, Michal Valko, Eva L. Dyer
Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction. CoRR (2021)
Ran Liu, Mehdi Azabou, Max Dabagia, Chi-Heng Lin, Mohammad Gheshlaghi Azar, Keith B. Hengen, Michal Valko, Eva L. Dyer
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity. NeurIPS (2021)
Audrunas Gruslys, Marc Lanctot, Rémi Munos, Finbarr Timbers, Martin Schmid, Julien Pérolat, Dustin Morrill, Vinícius Flores Zambaldi, Jean-Baptiste Lespiau, John Schultz, Mohammad Gheshlaghi Azar, Michael Bowling, Karl Tuyls
The Advantage Regret-Matching Actor-Critic. CoRR (2020)
Zhaohan Daniel Guo, Bernardo Ávila Pires, Bilal Piot, Jean-Bastien Grill, Florent Altché, Rémi Munos, Mohammad Gheshlaghi Azar
Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning. ICML (2020)
Rémi Munos, Julien Pérolat, Jean-Baptiste Lespiau, Mark Rowland, Bart De Vylder, Marc Lanctot, Finbarr Timbers, Daniel Hennes, Shayegan Omidshafiei, Audrunas Gruslys, Mohammad Gheshlaghi Azar, Edward Lockhart, Karl Tuyls
Fast computation of Nash Equilibria in Imperfect Information Games. ICML (2020)
Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Ávila Pires, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning. CoRR (2020)
Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Ávila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko
Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning. NeurIPS (2020)
Zhaohan Daniel Guo, Bernardo Ávila Pires, Bilal Piot, Jean-Bastien Grill, Florent Altché, Rémi Munos, Mohammad Gheshlaghi Azar
Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning. CoRR (2020)
Anna Harutyunyan, Will Dabney, Thomas Mesnard, Mohammad Gheshlaghi Azar, Bilal Piot, Nicolas Heess, Hado van Hasselt, Gregory Wayne, Satinder Singh, Doina Precup, Rémi Munos
Hindsight Credit Assignment. NeurIPS (2019)
Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alexander Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin J. Miller, Mohammad Gheshlaghi Azar, Ian Osband, Neil C. Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg
Meta-learning of Sequential Strategies. CoRR (2019)
Anna Harutyunyan, Will Dabney, Thomas Mesnard, Mohammad Gheshlaghi Azar, Bilal Piot, Nicolas Heess, Hado van Hasselt, Greg Wayne, Satinder Singh, Doina Precup, Rémi Munos
Hindsight Credit Assignment. CoRR (2019)
Mohammad Gheshlaghi Azar, Bilal Piot, Bernardo A. Pires, Jean-Bastien Grill, Florent Altché, Rémi Munos
World Discovery Models. CoRR (2019)
Tobias Pohlen, Bilal Piot, Todd Hester, Mohammad Gheshlaghi Azar, Dan Horgan, David Budden, Gabriel Barth-Maron, Hado van Hasselt, John Quan, Mel Vecerík, Matteo Hessel, Rémi Munos, Olivier Pietquin
Observe and Look Further: Achieving Consistent Performance on Atari. CoRR (2018)
Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Gheshlaghi Azar, David Silver
Rainbow: Combining Improvements in Deep Reinforcement Learning. AAAI (2018)
Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Bernardo A. Pires, Toby Pohlen, Rémi Munos
Neural Predictive Belief Representations. CoRR (2018)
Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Matteo Hessel, Ian Osband, Alex Graves, Volodymyr Mnih, Rémi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg
Noisy Networks For Exploration. ICLR (Poster) (2018)
Audrunas Gruslys, Will Dabney, Mohammad Gheshlaghi Azar, Bilal Piot, Marc G. Bellemare, Rémi Munos
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning. ICLR (Poster) (2018)
Mohammad Gheshlaghi Azar, Ian Osband, Rémi Munos
Minimax Regret Bounds for Reinforcement Learning. CoRR (2017)
Mohammad Gheshlaghi Azar, Ian Osband, Rémi Munos
Minimax Regret Bounds for Reinforcement Learning. ICML (2017)
Audrunas Gruslys, Mohammad Gheshlaghi Azar, Marc G. Bellemare, Rémi Munos
The Reactor: A Sample-Efficient Actor-Critic Architecture. CoRR (2017)
Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Rémi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg
Noisy Networks for Exploration. CoRR (2017)
Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Daniel Horgan, Bilal Piot, Mohammad Gheshlaghi Azar, David Silver
Rainbow: Combining Improvements in Deep Reinforcement Learning. CoRR (2017)
Vicenç Gómez, Mohammad Gheshlaghi Azar, Hilbert J. Kappen
Correcting Multivariate Auto-Regressive Models for the Influence of Unobserved Common Input. CCIA (2016)
Mohammad Gheshlaghi Azar, Eva L. Dyer, Konrad P. Körding
Convex Relaxation Regression: Black-Box Optimization of Smooth Functions by Learning Their Convex Envelopes. UAI (2016)
Mohammad Gheshlaghi Azar, Eva L. Dyer, Konrad P. Körding
Convex Relaxation Regression: Black-Box Optimization of Smooth Functions by Learning Their Convex Envelopes. CoRR (2016)
Mohammad Gheshlaghi Azar, Alessandro Lazaric, Emma Brunskill
Online Stochastic Optimization under Correlated Bandit Feedback. ICML (2014)
Mohammad Gheshlaghi Azar, Alessandro Lazaric, Emma Brunskill
Stochastic Optimization of a Locally Smooth Function under Correlated Bandit Feedback. CoRR (2014)
Mohammad Gheshlaghi Azar, Alessandro Lazaric, Emma Brunskill
Sequential Transfer in Multi-armed Bandit with Finite Set of Models. NIPS (2013)
Mohammad Gheshlaghi Azar, Rémi Munos, Hilbert J. Kappen
Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model. Mach. Learn. 91 (3) (2013)
Mohammad Gheshlaghi Azar, Alessandro Lazaric, Emma Brunskill
Sequential Transfer in Multi-armed Bandit with Finite Set of Models. CoRR (2013)
Mohammad Gheshlaghi Azar, Alessandro Lazaric, Emma Brunskill
Regret Bounds for Reinforcement Learning with Policy Advice. ECML/PKDD (1) (2013)
Mohammad Gheshlaghi Azar, Alessandro Lazaric, Emma Brunskill
Regret Bounds for Reinforcement Learning with Policy Advice CoRR (2013)
Mohammad Gheshlaghi Azar, Vicenç Gómez, Hilbert J. Kappen
Dynamic policy programming. J. Mach. Learn. Res. 13 (2012)
Mohammad Gheshlaghi Azar, Rémi Munos, Bert Kappen
On the Sample Complexity of Reinforcement Learning with a Generative Model . ICML (2012)
Mohammad Gheshlaghi Azar, Rémi Munos, Mohammad Ghavamzadeh, Hilbert J. Kappen
Speedy Q-Learning. NIPS (2011)
Mohammad Gheshlaghi Azar, Vicenç Gómez, Bert Kappen
Dynamic Policy Programming with Function Approximation. AISTATS (2011)
Mohammad Gheshlaghi Azar, Hilbert J. Kappen
Dynamic Policy Programming CoRR (2010)